Add observability module: Spring AI built-in meters and spans, cost per endpoint from token usage, Prometheus and Grafana dashboard

Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01JXVi2GMQ7bR5EmbUFdDj7N

observability/output/02-tool-call-spans.txt

@@ -0,0 +1,24 @@
+# Span tree for GET /weather?city=Pune (one tool call, two model calls)
+
+http get /weather  [SERVER]
+  spring_ai chat_client  [INTERNAL]
+    tool _calling   [INTERNAL]
+      call  [INTERNAL]
+        chat gpt-4o-mini  [INTERNAL]
+          POST  [CLIENT]
+      execute_tool getWeather  [INTERNAL]
+      call  [INTERNAL]
+        chat gpt-4o-mini  [INTERNAL]
+          POST  [CLIENT]
+
+attribute keys on the model-call spans:
+  gen_ai.operation.name
+  gen_ai.request.model
+  gen_ai.response.finish_reasons
+  gen_ai.response.id
+  gen_ai.response.model
+  gen_ai.system
+  gen_ai.usage.input_tokens
+  gen_ai.usage.output_tokens
+  gen_ai.usage.total_tokens
+  spring.ai.model.request.tool.names